Machine Vision of Animals and their Behaviour

10th September 2015, Swansea, UK

A half-day workshop held in conjunction with the 26th British Machine Vision Conference (BMVC).


Foreword

The Machine Vision of Animals and their Behaviour (MVAB) workshop brought together members of the community researching computer vision for animals, from such diverse application areas as wildlife study, animal farming, and industrial inspection.

We were pleased to present a programme featuring nine papers by authors from six countries (mostly in Europe, with a contribution from Australia), affiliated to 13 universities, two companies and one governmental body. Three papers were related with food production (milk, chicken livers, and fish), two of them addressing post-mortem inspection. Six other papers focused on the study of animals in the wild, ranging from very small brine shrimps to great white sharks, not forgetting crested black macaques, various birds, reef fish, and butterflies.

Echoing the diversity of application areas covered in the selected papers, the workshop’s oral sessions started with two stimulating keynote speeches from very different perspectives: Prof. Ilias Kyriazakis addressed aspects of livestock production that can potentially benefit from the use of computer vision, whereas Prof. Robert Fisher discussed the wide range of applications of the Fish4Knowledge database.

From the onset we envisaged that all accepted papers would be published, in order to make the call for papers as appealing as possible. Each paper was reviewed by three programme committee members in a double-blind process and, ultimately, we accepted all papers that had no recommendation for rejection from any reviewer. This resulted in nine accepted manuscripts out of 15 submissions, or a 60% acceptance rate. In order to ensure time for discussion after each oral presentation, while keeping the talks themselves reasonable in length, we scheduled six oral presentations and dedicated a poster session to the remaining three papers.

A best paper certificate was awarded to Geoffrey French, Mark H. Fisher, Michal Mackiewicz, and Coby L. Needle, from the University of East Anglia and Marine Scotland, for their paper on “Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video”, which received the highest reviewer scores.


Workshop Programme

The official online proceedings are hosted on BMVC's web site.

13:15 - 13:30 Setup
13:30 - 13:35 Welcome
13:35 - 14:20 Keynote by Ilias Kyriazakis

What can machine vision do for livestock?

Ilias Kyriazakis, Newcastle University

14:20 - 15:00 Livestock

Non-intrusive automated measurement of dairy cow body condition using 3D video

Mark Hansen (University of the West of England), Melvyn Smith (University of the West of England), Lyndon Smith (University of the West of England) and Duncan Forbes (Kingshay Conservation and Farming Ltd.)

Detecting Gallbladders in Chicken Livers using Spectral Imaging

Anders Jørgensen (Aalborg University), Eigil Mølvig Jensen (IHFood) and Thomas B. Moeslund (Aalborg University)

15:00 - 15:50 Coffee break and Poster Session (Located in Taliesin Annexe)

A Computer Vision Approach to Classification of Birds in Flight from Video Sequences

John Atanbori (University of Lincoln), John Murray (University of Lincoln), Wenting Duan (University of Lincoln), Kofi Appiah (Nottingham Trent University) and Patrick Dickinson (University of Lincoln)

Microfluidic environment and tracking analysis for the observation of Artemia Franciscana

Jose Alonso Solis-Lemus (City University London), Yushi Huang (RMIT University), Donald Wlodkowic (RMIT University) and Constantino Carlos Reyes-Aldasoro (City University London)

Invariant Image-Based Species Classification of Butterflies and Reef Fish

Hafeez Anwar (Vienna University of Technology), Sebastian Zambanini (Vienna University of Technology) and Martin Kampel (Vienna University of Technology)

15:50 - 16:35 Keynote by Robert Fisher

Fish detection, tracking, recognition, and analysis with the Fish4Knowledge dataset

Robert Fisher, University of Edinburgh

16:35 - 18:00 Fish and Macaque

Croatian Fish Dataset: Fine-grained classification of fish species in their natural habitat

Jonas Jäger (Hochschule Fulda), Marcel Simon (Friedrich Schiller University Jena), Joachim Denzler (Friedrich Schiller University Jena), Viviane Wolff (Hochschule Fulda), Klaus Fricke-Neuderth (Hochschule Fulda) and Claudia Kruschel (University of Zadar)

Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video

Geoffrey French (University of East Anglia), Mark Fisher (University of East Anglia), Michal Mackiewicz (University of East Anglia) and Coby Needle (Marine Scotland)

Affinity Matting for Pixel-accurate Fin Shape Recovery from Great White Shark Imagery

Benjamin Hughes (University of Bristol) and Tilo Burghardt (University of Bristol)

Detecting and Tracking Bottoms and Faces of the Crested Black Macaque in the Wild

John Chiverton (University of Portsmouth), Jerome Micheletta (University of Portsmouth) and Bridget Waller (University of Portsmouth)


Keynote Speakers

P​rof. Ilias Kyriazakis, Professor of Animal Health (Newcastle University, UK)

Prof. Ilias Kyriazakis is the Professor of Animal Health at the School of Agriculture, Food and Rural Development of Newcastle University. He is a veterinarian who specialises on the impact of management on the health and welfare of livestock. A substantial part of his work has been devoted to the development of capturing and analysing animal behaviour, and investigating the impact of management practices on them. He works across species and has addressed such issues from animals ranging from mice to cows. He has close collaborations with computer scientists and statisticians at Newcastle University and elsewhere, and examples of his current projects include the ‘Automated detection of pathologies on pig carcasses at abattoir’ and the ‘Automated monitoring of behavioural changes in livestock as means of early detection of health and welfare problems’. He holds visiting professorships in several North American and European Universities, and he is a Fellow of learned Societies in recognition of his work.

P​rof. Robert Fisher,​ Professor of Computer Vision (University of Edinburgh, UK)

Prof. Robert Fisher, BS (California Institute of Technology), MS (Stanford), PhD (Edinburgh) is a professor in the School of Informatics at the University of Edinburgh. His research covers topics in 3D computer vision and video sequence understanding. He has contributed to a spin-off company, Dimensional Imaging. The research has led to 13 authored or edited books and more than 250 peer-reviewed scientific articles or book chapters. He has developed several popular on-line computer vision resources. Most recently, he has been the coordinator of the EC funded Fish4Knowledge project acquiring and analysing video data of 1.4 billion fish from over about 10 camera-years of undersea video of tropical coral reefs. He is a Fellow of the Int. Association for Pattern Recognition (2008) and the British Machine Vision Association (2010).


Acknowledgements

We would like to express our gratitude to all authors who submitted their work, making the workshop possible; to the members of the programme committee, for their timely reviewing work, which enabled us to come up with a balanced, high-quality programme; to Prof. Ilias Kyriazakis, for his availability to contribute with a challenging keynote speech; to the BMVC organisers, Xianghua Xie, Gary Tam, and Mark Jones, for their prompt help with all our administrative queries; and naturally to all delegates who chose to participate in our workshop.

Our thanks also for the permission to use some images from the papers to illustrate the workshop's programme and web page, granted by the authors and by Michael C. Scholl of the Save Our Seas Foundation (shark fin image).


People

Chairs

Telmo Amaral (Newcastle University, UK)
Stephen Matthews (Newcastle University, UK)
Thomas Plötz (Newcastle University, UK)
Stephen McKenna (University of Dundee, UK)
Robert Fisher (University of Edinburgh, UK)

Programme Committee

Alexandra Branzan Albu (University of Victoria, Canada)
Douglas Armstrong (University of Edinburgh, UK)
Vinay Bettadapura (Georgia Institute of Technology, US)
Elsbeth van Dam (Noldus Information Technology, Netherlands)
Patrick Dickinson (University of Lincoln, UK)
Alfonso Pérez-Escudero (Massachusetts Institute of Technology, US)
Yasuyo Kita (National Institute of Advanced Industrial Science and Technology, Japan)
Anders Ringgaard Kristensen (University of Copenhagen, Denmark)
Eric Pauwels (Centrum Wiskunde & Informatica, Netherlands)
Sai Ravela (Massachusetts Institute of Technology, US)
Georgios Tzimiropoulos (Nottingham University, UK)




Warning: date(): It is not safe to rely on the system's timezone settings. You are *required* to use the date.timezone setting or the date_default_timezone_set() function. In case you used any of those methods and you are still getting this warning, you most likely misspelled the timezone identifier. We selected the timezone 'UTC' for now, but please set date.timezone to select your timezone. in /var/www/html/mvab2015/index.php on line 230
Last modified on 11 February 2016 17:04:03

Built on Skeleton framework